# Boson

> Build with Higgs Realtime, Higgs TTS 3, and Higgs Avatar APIs.

## Docs

- [Welcome to Boson AI](https://docs.boson.ai/overview.md): Choose the Higgs API for live conversation, generated speech, or talking-avatar video.
- [Authentication](https://docs.boson.ai/authentication.md): Authenticate Boson API requests with a Bearer token.
- [Pricing](https://docs.boson.ai/pricing.md): View Boson AI model and API pricing.
- [Overview](https://docs.boson.ai/models/higgs-realtime/overview.md): Build realtime voice assistants over WebSocket with streaming audio, text, turn detection, and tool calling.
- [Connections and sessions](https://docs.boson.ai/models/higgs-realtime/guides/connections-and-sessions.md): Connect over WebSocket, authenticate safely, configure a session, and choose Realtime and transcription models.
- [Audio and voices](https://docs.boson.ai/models/higgs-realtime/guides/audio-and-voices.md): Choose a Realtime voice, audio codec, and sample rate.
- [Turn detection and interruptions](https://docs.boson.ai/models/higgs-realtime/guides/turn-detection-and-interruptions.md): Configure automatic or manual turns and keep the conversation aligned during barge-in.
- [Tool use](https://docs.boson.ai/models/higgs-realtime/guides/tool-calling.md): Declare functions, execute tool calls in your application, return results, and continue the Realtime response.
- [Migrate an existing integration](https://docs.boson.ai/models/higgs-realtime/migrate-an-existing-integration.md): Move an OpenAI Realtime integration to Higgs Realtime and review the protocol compatibility differences.
- [LiveKit](https://docs.boson.ai/models/higgs-realtime/integrations/livekit.md): LiveKit support status for Higgs Realtime, and what to use in the meantime.
- [Pipecat](https://docs.boson.ai/models/higgs-realtime/integrations/pipecat.md): Use Higgs Realtime as a speech-to-speech service in a Pipecat pipeline.
- [Overview](https://docs.boson.ai/models/higgs-tts/overview.md): Chat-native text-to-speech with streaming, 100 languages, instant voice cloning, and inline emotion and style control.
- [Voices](https://docs.boson.ai/models/higgs-tts/voices.md): Use preset voices, reference audio, or reusable custom voices with Higgs TTS 3.
- [Languages](https://docs.boson.ai/models/higgs-tts/languages.md): Higgs TTS 3 supports 102 languages with single-digit WER/CER.
- [Tags](https://docs.boson.ai/models/higgs-tts/tags.md): Inline control tokens that shape emotion, style, prosody, and sound effects inside the input text.
- [Overview](https://docs.boson.ai/models/higgs-avatar/overview.md): Generate talking-head video from a still image and a driving voice or text.
- [Inputs and limits](https://docs.boson.ai/models/higgs-avatar/input-options.md): Choose audio or text input, upload local assets, and check Higgs Avatar sizes, limits, and common errors.
- [Streaming video](https://docs.boson.ai/models/higgs-avatar/streaming-video.md): Receive fragmented MP4 from Higgs Avatar so playback can begin before generation finishes.
- [Overview](https://docs.boson.ai/api-reference/realtime/overview.md): Connect to Higgs Realtime and navigate the REST and WebSocket protocol reference.
- [Create a client secret](https://docs.boson.ai/api-reference/realtime/client-secrets.md): Mint a short-lived credential for browser and client-side Higgs Realtime connections.
- [Client events](https://docs.boson.ai/api-reference/realtime/client-events.md): Configure a Realtime session, provide input, manage conversation items, and control responses.
- [Server events](https://docs.boson.ai/api-reference/realtime/server-events.md): Handle session state, input audio, streamed responses, tool calls, errors, and lifecycle events.
- [Create a speech](https://docs.boson.ai/api-reference/audio/create-a-speech.md): Generate speech audio from text. Returns an audio file, or a stream of raw PCM chunks when `stream` is `true`. The body may be JSON or `multipart/form-data` — the latter lets you upload `ref_audio` as a raw file instead of base64-encoding it.
- [Create a voice](https://docs.boson.ai/api-reference/audio/create-a-voice.md): Register a reusable reference voice for cloning. Identical audio re-registered under the same API key returns the existing voice. Pass the returned `voice` ID to the `voice` field of `POST /v1/audio/speech` instead of sending `ref_audio` on every request.
- [List voices](https://docs.boson.ai/api-reference/audio/list-voices.md): List the reference voices registered under your API key.
- [Get a voice](https://docs.boson.ai/api-reference/audio/get-a-voice.md): Fetch a single reference voice by ID.
- [Create a video](https://docs.boson.ai/api-reference/videos/create-a-video.md): Create an avatar talking-head video (async). Returns the Video object with `status: "queued"`; poll `GET /v1/videos/{video_id}` and download the rendered MP4 from `GET /v1/videos/{video_id}/content`. Provide a reference image plus exactly one driving input — `input` (audio-to-video) or `input_tts` (…
- [Retrieve a video](https://docs.boson.ai/api-reference/videos/retrieve-a-video.md): Retrieve the Video object (status / progress). Always JSON — the rendered MP4 is downloaded from `GET /v1/videos/{video_id}/content`.
- [Download content](https://docs.boson.ai/api-reference/videos/download-content.md): Download the rendered video. Returns the MP4 bytes (`variant=video`, the default). `404` until the video is `completed`.
- [Create a video (streaming)](https://docs.boson.ai/api-reference/videos/create-a-video-streaming.md): Same request body as `POST /v1/videos`, but the response body IS the live fragmented-MP4 (fMP4) byte stream — frames arrive as they are generated, so playback can start before the clip is complete. The video id rides back in the `X-Video-Id` header; the full MP4 is stored too, so a later `GET /v1/vi…

## OpenAPI Specs

- [openapi](https://docs.boson.ai/openapi.json)